CN111178670A - Short-term low-voltage power distribution network data quality evaluation algorithm based on entropy weight inversion method - Google Patents

Short-term low-voltage power distribution network data quality evaluation algorithm based on entropy weight inversion method Download PDF

Info

Publication number
CN111178670A
CN111178670A CN201911196169.8A CN201911196169A CN111178670A CN 111178670 A CN111178670 A CN 111178670A CN 201911196169 A CN201911196169 A CN 201911196169A CN 111178670 A CN111178670 A CN 111178670A
Authority
CN
China
Prior art keywords
data
formula
data set
logs
redundancy
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911196169.8A
Other languages
Chinese (zh)
Inventor
陈西寅
冉小康
陈渝
李志勇
梁瑜
苏通
李炳泉
陈伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Zhicheng Electronic Technology Co ltd
Beibei Power Supply Co of State Grid Chongqing Electric Power Co Ltd
Original Assignee
Hangzhou Zhicheng Electronic Technology Co ltd
Beibei Power Supply Co of State Grid Chongqing Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Zhicheng Electronic Technology Co ltd, Beibei Power Supply Co of State Grid Chongqing Electric Power Co Ltd filed Critical Hangzhou Zhicheng Electronic Technology Co ltd
Priority to CN201911196169.8A priority Critical patent/CN111178670A/en
Publication of CN111178670A publication Critical patent/CN111178670A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06395—Quality analysis or management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Energy or water supply

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • Game Theory and Decision Science (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Water Supply & Treatment (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Supply And Distribution Of Alternating Current (AREA)
  • Remote Monitoring And Control Of Power-Distribution Networks (AREA)

Abstract

The invention provides a short-term low-voltage distribution network data quality evaluation algorithm based on an entropy weight method, which comprises the following steps: the method comprises the following steps: extracting equipment data, platform area data and user data in a certain time period from the big data platform ODPS; step two: calculating the accuracy; step three: calculating the integrity; step four: calculating the timeliness; step five: calculating the redundancy; step six: weighting the evaluation indexes, namely assigning a weight coefficient to the evaluation indexes of the data quality by adopting an entropy weight resisting method; step seven: and calculating a comprehensive score. The method can reflect the quality of the data and provide feasibility reference for data modeling.

Description

Short-term low-voltage power distribution network data quality evaluation algorithm based on entropy weight inversion method
Technical Field
The invention relates to the field of intelligent power grid data mining, in particular to a short-term low-voltage distribution network data quality evaluation algorithm based on an entropy weight method.
Background
In recent years, national grid companies deeply research the construction of 'big cloud and thing movement' marketing bases with cloud computing, internet of things, big data and mobile internet as themes, develop top-level design of new technology application, platform construction, pilot point verification and partial popularization and application, and provide good support for strong smart grid construction and company operators. If the traditional technical means is continuously used, the requirement for the current day-to-day expansion of collected data, user data and equipment data cannot be met, so that a new generation of mass data storage and analysis medium taking a large data platform as a support becomes a key point of technical innovation of a power grid company. For example, the thunberg electric power company builds a "thunberg cloud" big data development platform by using the aleuritum Open Data Processing Service (ODPS) to store and accelerate the long-and-short-term operation big data analysis process. However, because the data acquired by the smart grid acquisition device has errors, an objective evaluation system of short-term operation data of a large data platform needs to be established to reflect the quality of the data, and feasible reference is provided for data modeling.
Disclosure of Invention
In order to solve certain technical problems or some technical problems in the prior art, the invention provides a short-term low-voltage distribution network data quality evaluation algorithm based on an inverse entropy weight method, which can reflect the quality of data and provide feasible reference for data modeling.
In order to solve the above-mentioned existing technical problem, the invention adopts the following scheme: the short-term low-voltage power distribution network data quality evaluation algorithm based on the entropy weight method comprises the following steps:
the method comprises the following steps: extracting equipment data, platform area data and user data in a certain time period from the big data platform ODPS;
step two: the accuracy of the calculation is given by the formula:
Figure BDA0002294672160000021
in the formula, AcIs the accuracy of the data set; n isallIs the total amount of data; n is0The log number is the log number with unqualified accuracy in the data set; n isnullThe number of logs with data missing phenomenon exists in the data set; n isrThe number of logs with data redundancy phenomenon exists in the data set;
step three: the integrity is calculated by the following formula:
Figure BDA0002294672160000022
in the formula, AeIs the accuracy of the data set; n isallIs the total amount of data; n isnullThe number of logs with data missing phenomenon exists in the data set; n isrThe number of logs with data redundancy phenomenon exists in the data set;
step four: calculating the timeliness, and the formula is as follows:
Figure BDA0002294672160000023
wherein A isdIs the timeliness of the data set; n isdJudging the number of logs which are not timely;
step five: calculating the redundancy, and the formula is as follows:
Figure BDA0002294672160000024
wherein A isrRedundancy for the data set;
step six: weighting the evaluation indexes, namely assigning a weight coefficient to the evaluation indexes of the data quality by adopting an entropy weight resisting method;
step seven: and calculating a comprehensive score.
Preferably, the method for data quality in step six adopts an entropy weight methodWhen the evaluation index is given a weight coefficient, an evaluation index matrix H is first constructedm×nWherein m is the number of logs, n is an evaluation index, and the information is subjected to inverse entropy
Figure BDA0002294672160000031
Figure BDA0002294672160000032
The weight coefficient of each evaluation index can thus be obtained by:
Figure BDA0002294672160000033
wherein k isjIs the weight coefficient of the jth evaluation index.
Preferably, when the comprehensive score is calculated in the seventh step, after the scores of the accuracy, the integrity, the timeliness and the redundancy and the weight coefficient are obtained, the quality comprehensive score of the extracted short-term operation data is obtained through the following formula:
Figure BDA0002294672160000034
in the formula, AallFor composite scoring, Aall∈[0,100](ii) a When j is 1, Aj＝AcI.e. accuracy; when j is 2, Aj＝AeI.e. integrity; when j is 3, Aj＝AdI.e. integrity; when j is 4, Aj＝ArI.e. redundancy.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a short-term low-voltage power distribution network data quality evaluation algorithm based on an entropy weight method, which can reflect the quality of data and provide feasible reference for data modeling.
Detailed Description
The present invention is further described below with reference to specific embodiments, and it should be noted that, without conflict, any combination between the embodiments or technical features described below may form a new embodiment.
The invention provides a short-term low-voltage distribution network data quality evaluation algorithm based on an entropy weight method, which comprises the following steps:
the method comprises the following steps: extracting equipment data, platform area data and user data in a certain time period from the big data platform ODPS;
step two: the accuracy of the calculation is given by the formula:
Figure BDA0002294672160000041
in the formula, AcIs the accuracy of the data set; n isallIs the total amount of data; n is0The log number is the log number with unqualified accuracy in the data set; n isnullThe number of logs with data missing phenomenon exists in the data set; n isrThe number of logs with data redundancy phenomenon exists in the data set;
step three: the integrity is calculated, and because the phenomenon that the intelligent power grid data acquisition device or the communication device breaks down cannot be avoided, a null state, namely a data loss phenomenon, occurs to influence the integrity of a data set, and the formula is as follows:
Figure BDA0002294672160000042
in the formula, AeIs the accuracy of the data set; n isallIs the total amount of data; n isnullThe number of logs with data missing phenomenon exists in the data set; n isrThe number of logs with data redundancy phenomenon exists in the data set;
step four: calculating the timeliness, wherein the data acquisition intervals of the smart grid are generally 15 minutes, 30 minutes and 60 minutes, and if the ethernet network is jammed in the process, the timeliness problem of data return is affected, so that the timeliness of the data set needs to be scored, and the formula is as follows:
Figure BDA0002294672160000043
wherein A isdIs the timeliness of the data set; n isdJudging the number of logs which are not timely;
step five: the redundancy is calculated, and the reason for the data redundancy of the low-voltage distribution network is mainly that the same data is transmitted back for many times, so the lower the redundancy of the data set is, the better the data quality is, and the formula is as follows:
Figure BDA0002294672160000044
wherein A isrRedundancy for the data set;
step six: weighting the evaluation index, assigning weight coefficient to the evaluation index of data quality by selecting an anti-entropy weight method, and firstly constructing an evaluation index matrix Hm×nWherein m is the number of logs, n is an evaluation index, and the information is subjected to inverse entropy
Figure BDA0002294672160000051
Figure BDA0002294672160000052
The weight coefficient of each evaluation index can thus be obtained by:
Figure BDA0002294672160000053
wherein k isjA weight coefficient of the jth evaluation index;
step seven: calculating comprehensive scores, and after obtaining scores of accuracy, integrity, timeliness and redundancy and weight coefficients, obtaining quality comprehensive scores of the extracted short-term operation data through the following formula:
Figure BDA0002294672160000054
in the formula, AallFor composite scoring, Aall∈[0,100](ii) a When j is 1, Aj＝AcI.e. accuracy; when j is 2, Aj＝AeI.e. integrity; when j is 3, Aj＝AdI.e. integrity; when j is 4, Aj＝ArI.e. redundancy.
The data quality is good when the score is (90, 100), good when the score is (70, 90), general when the score is (60, 70), and poor when the score is (0, 60).
Taking a medium-voltage line with a certain 10kV voltage level of a national power grid city company and 1 subordinate low-voltage transformer area as an example, the line and the low-voltage transformer area are analyzed. The data storage conditions of the low-voltage distribution network are shown in table 1:
table 1 short-term data quality table for certain low-voltage distribution network in short term of power grid
Figure BDA0002294672160000061
The method can reflect the quality of the data and provide feasibility reference for data modeling.
The above embodiments are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are within the protection scope of the present invention.

Claims (3)

1. The short-term low-voltage power distribution network data quality evaluation algorithm based on the entropy weight method comprises the following steps:
the method comprises the following steps: extracting equipment data, platform area data and user data in a certain time period from the big data platform ODPS;
step two: the accuracy of the calculation is given by the formula:
Figure FDA0002294672150000011
in the formula, AcIs the accuracy of the data set; n isallIs the total amount of data; n is0The number of logs with unqualified accuracy in the data set is determined; n isnullThe number of logs with data missing phenomenon exists in the data set; n isrThe number of logs with data redundancy phenomenon exists in the data set;
step three: the integrity is calculated by the following formula:
Figure FDA0002294672150000012
in the formula, AeIs the accuracy of the data set; n isallIs the total amount of data; n isnullThe number of logs with data missing phenomenon exists in the data set; n isrThe number of logs with data redundancy phenomenon exists in the data set;
step four: calculating the timeliness, and the formula is as follows:
Figure FDA0002294672150000013
wherein A isdIs the timeliness of the data set; n isdJudging the number of logs which are not timely;
step five: calculating the redundancy, and the formula is as follows:
Figure FDA0002294672150000014
wherein A isrRedundancy for the data set;
step six: weighting the evaluation indexes, namely assigning a weight coefficient to the evaluation indexes of the data quality by adopting an entropy weight resisting method;
step seven: and calculating a comprehensive score.
2. The method of claim 1Short-term low-voltage distribution network data quality evaluation algorithm based on entropy weight method is characterized in that: when the weight coefficient is given to the evaluation index of the data quality by using the inverse entropy weight method in the sixth step, firstly, an evaluation index matrix H is constructedm×nWherein m is the number of logs, n is an evaluation index, and the information is subjected to inverse entropy
Figure FDA0002294672150000021
Figure FDA0002294672150000022
The weight coefficient of each evaluation index can thus be obtained by:
Figure FDA0002294672150000023
wherein k isjIs the weight coefficient of the jth evaluation index.
3. The entropy weight method-based short-term low-voltage distribution network data quality evaluation algorithm according to claim 2, characterized in that: when the comprehensive score is calculated in the step seven, after the scores of the accuracy, the integrity, the timeliness and the redundancy and the weight coefficient are obtained, the quality comprehensive score of the extracted short-term operation data is obtained through the following formula:
Figure FDA0002294672150000024
in the formula, AallFor composite scoring, Aall∈[0,100](ii) a When j is 1, Aj＝AcI.e. accuracy; when j is 2, Aj＝AeI.e. integrity; when j is 3, Aj＝AdI.e. integrity; when j is 4, Aj＝ArI.e. redundancy.
CN201911196169.8A 2019-11-29 2019-11-29 Short-term low-voltage power distribution network data quality evaluation algorithm based on entropy weight inversion method Pending CN111178670A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911196169.8A CN111178670A (en) 2019-11-29 2019-11-29 Short-term low-voltage power distribution network data quality evaluation algorithm based on entropy weight inversion method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911196169.8A CN111178670A (en) 2019-11-29 2019-11-29 Short-term low-voltage power distribution network data quality evaluation algorithm based on entropy weight inversion method

Publications (1)

Publication Number Publication Date
CN111178670A true CN111178670A (en) 2020-05-19

Family

ID=70647301

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911196169.8A Pending CN111178670A (en) 2019-11-29 2019-11-29 Short-term low-voltage power distribution network data quality evaluation algorithm based on entropy weight inversion method

Country Status (1)

Country Link
CN (1) CN111178670A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111898871A (en) * 2020-07-08 2020-11-06 南京南瑞水利水电科技有限公司 Power grid power end data quality evaluation method, device and system

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100138478A1 (en) * 2007-05-08 2010-06-03 Zhiping Meng Method of using information set in video resource
CN103996147A (en) * 2014-03-20 2014-08-20 国家电网公司 Comprehensive evaluation method for power distribution network
CN108229784A (en) * 2017-11-09 2018-06-29 中国电力科学研究院有限公司 The multidimensional data quality evaluating method and system of a kind of intelligent distribution network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100138478A1 (en) * 2007-05-08 2010-06-03 Zhiping Meng Method of using information set in video resource
CN103996147A (en) * 2014-03-20 2014-08-20 国家电网公司 Comprehensive evaluation method for power distribution network
CN108229784A (en) * 2017-11-09 2018-06-29 中国电力科学研究院有限公司 The multidimensional data quality evaluating method and system of a kind of intelligent distribution network

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
潘旭: "智能配电网多维数据质量评价方法" *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111898871A (en) * 2020-07-08 2020-11-06 南京南瑞水利水电科技有限公司 Power grid power end data quality evaluation method, device and system
CN111898871B (en) * 2020-07-08 2023-07-18 南京南瑞水利水电科技有限公司 Method, device and system for evaluating data quality of power grid power supply end

Similar Documents

Publication Publication Date Title
CN107909253B (en) Intelligent power distribution network scheduling control effect evaluation method based on inter-zone analytic method
CN110705873B (en) Power distribution network running state portrait analysis method
CN103744850B (en) A kind of electrical network disaster real-time monitoring device and method based on intuitionistic fuzzy-rough sets
CN106780128B (en) Power distribution network reliability evaluation method
CN109655712A (en) A kind of distribution network line fault analysis of causes method and system
CN106777150A (en) A kind of cross-system data transfer device for merging operation of power networks environment and facility information
CN105069692A (en) Accurate power grid safety risk assessment method
Dehghani et al. Multi-stage resilience management of smart power distribution systems: A stochastic robust optimization model
CN109064056A (en) A kind of Lightning stroke Protection Measures for Over-Head Lines selection method based on gray relative analysis method
CN112202597A (en) Method for evaluating importance of communication network node in low-voltage distribution area
CN111178670A (en) Short-term low-voltage power distribution network data quality evaluation algorithm based on entropy weight inversion method
CN107292759A (en) Distribution network planning based on power supply reliability calculates analysis system
CN105548779B (en) A kind of method for early warning and system of the idle operating status of low-voltage network
Guoliang et al. Evaluating power grid enterprise's investment returns
CN110717725B (en) Power grid project selection method based on big data analysis
CN107748819A (en) A kind of electrical secondary equipment modeling method and system based on natural language processing
CN110174713B (en) Power line strong convection weather monitoring and early warning method and device
CN114266370A (en) Method and system for generating fault handling plan of power grid equipment in typhoon meteorological environment on line and storage medium
Liu et al. Overhead transmission line condition assessment based on intention classification and slot filling using optimized BERT model
Liu et al. Historical Similar Ticket Matching and Extraction used for Power Grid Maintenance Work Ticket Decision Making
CN111144614A (en) Short-term low-voltage distribution network theoretical line loss prediction algorithm based on kmeans-LightGBM
CN115809761B (en) Voltage quality analysis method and system based on low-voltage transformer area
CN110472844A (en) A kind of evaluation control method for the intelligent distribution network containing miniature PMU device
CN114021395B (en) Method and device for analyzing fragile correlation of power information physical system line
Ge et al. Evaluation method of distribution network state based on IT-II-Fuzzy K-means Clustering Algorithm for Imbalanced Data under PIOT

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20200519

WD01 Invention patent application deemed withdrawn after publication